CN109615627B - Power transmission and transformation inspection image quality evaluation method and system - Google Patents
Power transmission and transformation inspection image quality evaluation method and system Download PDFInfo
- Publication number
- CN109615627B CN109615627B CN201811532907.7A CN201811532907A CN109615627B CN 109615627 B CN109615627 B CN 109615627B CN 201811532907 A CN201811532907 A CN 201811532907A CN 109615627 B CN109615627 B CN 109615627B
- Authority
- CN
- China
- Prior art keywords
- quality evaluation
- neural network
- image quality
- deep convolutional
- power transmission
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a power transmission and transformation inspection image quality evaluation method and a system, comprising the following steps: constructing a power transmission and transformation inspection image quality evaluation standard sample set; constructing a deep convolutional neural network, and performing weight tuning training on each layer of neural network; obtaining at least one deep convolutional neural network model; and according to the obtained deep convolutional neural network model, performing quality evaluation on the inspection image to be evaluated by utilizing forward reasoning calculation. The invention has the beneficial effects that: by constructing a deep convolutional neural network structure and carrying out tuning training on network parameters of each layer, the acquisition and quality evaluation of essential characteristics of the power transmission and transformation inspection image are realized, the robustness and accuracy of the quality evaluation of the inspection image are improved, and more effective image data are provided for the intelligent analysis of the inspection image in the later period.
Description
Technical Field
The invention relates to the field of intelligent analysis of power systems, in particular to a power transmission and transformation inspection image quality evaluation method and system.
Background
In order to ensure the normal operation of the power transmission line and the transformer substation, the unmanned aerial vehicle inspection and the intelligent inspection of the transformer substation robot become conventional inspection modes, and a large amount of inspection images can be generated during each inspection. Because illumination, haze, the in-process unmanned aerial vehicle of patrolling and examining and robot platform shake lead to gathering the image and appear fuzzy, the circumstances such as defocus appear, very big reduction the characterization ability of image, improved the degree of difficulty that the image intelligent analysis was patrolled and examined in the later stage simultaneously. In order to ensure the validity of data and reduce the difficulty of intelligent image analysis, a manual interpretation mode is usually adopted for image quality evaluation and low-quality images are deleted, the labor intensity is high, evaluation fluctuation is large due to the influence of the experience of workers, and the consistency of quality evaluation cannot be ensured.
At the present stage, image quality evaluation is mainly divided into a subjective evaluation mode and an objective evaluation mode, the subjective evaluation mode is carried out by means of manual interpretation, and labor intensity is high; the objective evaluation mode mainly utilizes image vision correlation technology to construct image characteristic representation, and combines a correlation evaluation algorithm to automatically realize evaluation and analysis of image quality.
In the prior art, the image quality evaluation is carried out by using a local filtering and gradient matching mode, and the Log-Gabor is adopted for filtering processing, so that the multi-type characteristics of the image cannot be robustly extracted, and the application of the image quality evaluation method is limited.
The prior art proposes a method of a convolutional neural network to judge the image quality, and the method only designs a 5-layer network, can only extract local edge and texture characteristics, and cannot acquire deeper semantic and structural information of the image.
Due to the fact that the power transmission and transformation inspection images contain various target types and complex backgrounds, the method cannot effectively and accurately evaluate the quality of the inspection images.
Disclosure of Invention
The invention provides a power transmission and transformation inspection image quality evaluation method and system in order to solve the problems. Firstly, constructing a power transmission and transformation inspection image quality judgment standard sample set; secondly, designing a deep convolutional neural network structure, and training an image quality evaluation model by adjusting and training relevant parameters; and finally, performing a reasoning process of the image to be evaluated to obtain image quality evaluation parameters and finish image quality evaluation.
In order to achieve the purpose, the invention adopts the following technical scheme:
in one or more embodiments, a power transmission and transformation inspection image quality evaluation method is disclosed, which includes:
constructing a power transmission and transformation inspection image quality evaluation standard sample set;
constructing a deep convolutional neural network, and performing weight tuning training on each layer of neural network;
in the deep convolutional network model parameter training process, a network is pre-trained by utilizing a public data set, the parameters of the full connection layer are assigned in a random initialization mode, and the parameters of each layer are optimized by adopting a gradient descent method;
respectively training data randomly extracted from the power transmission and transformation inspection image quality evaluation standard sample set at least once to obtain at least one deep convolution neural network model;
and according to the obtained deep convolutional neural network model, performing quality evaluation on the inspection image to be evaluated by utilizing forward reasoning calculation.
Further, the power transmission and transformation inspection image quality evaluation standard sample set comprises two parts: the first part is a general AVA data set and a TID2013 data set of an image quality evaluation database; the second part is a power transmission and transformation inspection image after the manual evaluation;
further, the air conditioner is provided with a fan,
the ratio of the first portion to the second portion of training data is 1: 2.
Further, the constructing of the deep convolutional neural network specifically includes:
constructing an image quality evaluation deep convolutional neural network by taking the VGG19 network structure as a reference; the deep convolutional neural network includes: the device comprises a convolution layer, a pooling layer, a full-connection layer and a classification layer;
performing feature extraction on local areas of each layer by the convolutional layer; performing dimensionality reduction processing on the feature data after convolution processing on the pooling layer; the full connection layer collects local features to form uniform feature description of the image, and the uniform feature description is used as input of grading and classifying processing; and the classification layer is used for grading and classifying the data of the full connection layer.
Further, in order to evaluate the image quality, the soft-max cross entropy loss function of the VGG19 network is modified, the normalized EMD distance is used for measuring the loss of the image evaluation, and the calculation of the relative distance between each evaluation level of each image is realized.
Further, the normalized EMD distance is specifically:
wherein p ═ ps1,ps2,…,psN]，s1＜s2＜sNRepresenting the probability distribution of the image quality of the artificial annotation,
is the predicted image quality probability distribution in the training process; n is the marked grade;
r is a set parameter.
Further, according to the obtained deep convolutional neural network model, the quality of the inspection image is evaluated by utilizing forward reasoning calculation, and the method specifically comprises the following steps:
respectively loading at least one trained deep convolutional neural network model, and loading network parameters of each layer of each deep convolutional neural network model;
carrying out scaling operation on an input image, and carrying out mean value removal on the image;
for each deep convolutional neural network model, calculating a quality evaluation score of the input image through a deep convolutional neural network forward reasoning calculation process; outputting the score probability of the image data belonging to different grades at the last soft-max; calculate mean and standard deviation for score probability:
respectively calculating the mean value and the mean value of the standard deviation calculated by each depth convolution neural network model, and taking the mean values as image quality evaluation indexes; and evaluating the image quality according to the numerical value of the image quality evaluation index.
The power transmission and transformation inspection image quality evaluation system based on the deep convolutional neural network comprises a server, wherein the server comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, and the processor executes the program to realize any one of the power transmission and transformation inspection image quality evaluation methods based on the deep convolutional neural network.
In one or more embodiments, a computer-readable storage medium is disclosed, on which a computer program is stored, which, when executed by a processor, performs any of the above-described methods for evaluating the quality of an image of a power transmission and transformation inspection tour based on a deep convolutional neural network.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, by constructing a deep convolutional neural network structure and carrying out tuning training on network parameters of each layer, the acquisition of essential characteristics and quality evaluation of the power transmission and transformation inspection image are realized, the robustness and accuracy of the quality evaluation of the inspection image are improved, and more effective image data are provided for the intelligent analysis of the inspection image in the later period.
And by adopting a deeper convolutional neural network, the deep image characteristic information can be obtained.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a schematic diagram of a power transmission and transformation inspection image quality evaluation deep convolution network structure;
FIG. 2 is a flow chart of an image quality evaluation method of the deep convolutional neural network power transmission and transformation patrol inspection.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
In one or more embodiments, a method for evaluating the quality of an image of a power transmission and transformation patrol inspection based on a deep convolutional neural network is disclosed, as shown in fig. 2, and includes the following steps:
the method comprises the following steps: constructing a power transmission and transformation inspection image quality evaluation standard sample set, wherein the sample set mainly comprises two parts: one part is a general AVA data set and a TID2013 data set of the image quality evaluation database, and the other part is a power transmission and transformation inspection image after manual evaluation.
In order to ensure that the power transmission and transformation patrol inspection image occupies relative dominance, the proportion of two parts of training data used in the training process is 1: 2.
Step two: and constructing a deep convolutional neural network structure and functional parameters of each layer of the network, and performing weight tuning training on each layer of the network.
(1) And constructing an image quality evaluation deep convolutional neural network by taking the VGG19 network structure as a reference. The main network layer attributes are convolutional layer, pooling layer, full connection layer, and classification layer. The convolution layer mainly extracts the characteristics of a local area of each layer; the pooling layer is mainly used for performing dimension reduction processing on the feature data after convolution processing so as to improve the feature representation capability and reduce the data volume; the full connection layer mainly collects local features to form uniform feature description of the image, and the uniform feature description is used as input of grading and classifying processing; the classification layer mainly performs grading and classification on data of the full connection layer. The classification layer output is set to 10 according to the image quality evaluation level, and the specific network structure and network attribute parameters are shown in fig. 1.
(2) To evaluate image quality, the soft-max cross entropy loss function of the VGG19 network was modified to measure the loss of image evaluation using normalized EMD distance:
where p is [ p ]s1,ps2,…,psN]Wherein s is1＜s2＜sNRepresenting the image quality probability distribution of the artificial annotation,
is the predicted image quality probability distribution in the training process; n is the marked grade;
by utilizing the EMD distance, the calculation of the relative distance between each score of each image (i.e., loss penalty) is achieved. To facilitate the optimization calculation during training, the parameter r is set to 2 in practice.
(3) In the deep convolutional network model parameter training process, a network is pre-trained by using an ImageNet public data set so as to improve the training efficiency of network parameters and the robustness of the model; assigning the parameters of the full connection layer in a random initialization mode; during optimization, the parameter of each layer is optimized by adopting an Adam gradient descent method, the offset momentum parameter is set to be 0.9, and the random discarding parameter is set to be 0.75; learning efficiency was set to 3 x 10-6。
(4) In order to improve the robustness of image quality evaluation in application, the steps (2) and (3) are repeated in the training process, and the data randomly extracted from the sample library are trained for 4 times respectively to obtain 4 network models.
Step three: and (5) polling image quality evaluation reasoning. And loading the constructed deep convolutional neural network structure and each layer of weight parameters, and performing image quality evaluation and scoring.
After multiple times of training, an image evaluation depth convolution network model is obtained, the quality evaluation of the inspection image can be realized by utilizing the forward reasoning calculation of the convolution network, and the specific operation is as follows:
(1) respectively loading the trained 4 deep convolutional network structures, and loading the network parameters of each layer;
(2) pre-process the input image, perform scaling operations on the input image (to 256 × 256), and perform a de-averaging operation on the image:
Ii＝Ii-meani,i∈(1,3)
wherein, I is a pixel of the image, I represents the number of channels of the image, the image is a color three-channel (RGB) image, and three channels are the basic attributes of the color image. mean represents the mean of the image.
(3) And calculating the quality evaluation score through a convolutional network forward reasoning process. And outputting the score probability of 1-10 grades of image data at the last soft-max. Calculate mean and standard deviation for score probability:
wherein s isiThe image quality levels are 1-10 quality levels of the image respectively, and the value of i is 1,2,3 … and 10.
(4) And (5) executing the step (3)4 times to obtain the average value and the standard deviation of 4 groups of network reasoning, averaging the average value, and finally obtaining the image quality evaluation index:
taking the average value as a main evaluation index, wherein the higher the average value is, the better the image quality is; the mean values are the same, and the smaller the standard deviation, the better the image quality.
Example two
In other embodiments, a system for evaluating the quality of an image of a power transmission and transformation patrol inspection based on a deep convolutional neural network is disclosed, and includes a server, where the server includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method for evaluating the quality of an image of a power transmission and transformation patrol inspection based on a deep convolutional neural network as described in the first embodiment when executing the program.
EXAMPLE III
In other embodiments, a computer-readable storage medium is disclosed, on which a computer program is stored, which, when executed by a processor, performs the method for evaluating the image quality of the power transmission and transformation inspection tour based on the deep convolutional neural network described in the first embodiment.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (6)
1. The power transmission and transformation inspection image quality evaluation method is characterized by comprising the following steps:
constructing a power transmission and transformation inspection image quality evaluation standard sample set; the power transmission and transformation inspection image quality evaluation standard sample set comprises two parts: the first part is a general AVA data set and a TID2013 data set of an image quality evaluation database, the second part is a power transmission and transformation inspection image after manual evaluation, and the ratio of the training data of the first part to the training data of the second part is 1: 2;
constructing a deep convolutional neural network, and performing weight tuning training on each layer of neural network;
respectively training data randomly extracted from the power transmission and transformation inspection image quality evaluation standard sample set at least once to obtain at least one deep convolution neural network model;
carrying out quality evaluation on the inspection image to be evaluated by utilizing forward reasoning calculation; respectively calculating the average value and the average value of the standard deviation calculated by each depth convolution neural network model, using the average values and the average values as image quality evaluation indexes, and evaluating the image quality according to the numerical values of the image quality evaluation indexes;
and modifying the soft-max cross entropy loss function of the deep convolutional neural network, measuring the loss of image evaluation by using the normalized EMD distance, and realizing the calculation of the relative distance between each evaluation level of each image.
2. The method for evaluating the image quality of the power transmission and transformation inspection tour according to claim 1, wherein the constructing of the deep convolutional neural network specifically comprises:
constructing an image quality evaluation deep convolutional neural network by taking the VGG19 network structure as a reference; the deep convolutional neural network includes: the device comprises a convolution layer, a pooling layer, a full-connection layer and a classification layer;
performing feature extraction on local areas of each layer by the convolutional layer; performing dimensionality reduction processing on the feature data after convolution processing on the pooling layer; the full connection layer collects local features to form uniform feature description of the image, and the uniform feature description is used as input of grading and classifying processing; and the classification layer is used for grading and classifying the data of the full connection layer.
3. The power transmission and transformation inspection image quality evaluation method according to claim 1, wherein in the deep convolutional network model parameter training process, a network is pre-trained by using a public data set, full link layer parameters are assigned in a random initialization mode, and each layer of parameters are optimized by using a gradient descent method.
4. The method for evaluating the quality of the power transmission and transformation inspection image according to claim 1, wherein the quality of the inspection image is evaluated by utilizing forward reasoning calculation according to the obtained deep convolutional neural network model, and specifically the method comprises the following steps:
respectively loading at least one trained deep convolutional neural network model, and loading network parameters of each layer of each deep convolutional neural network model;
carrying out scaling operation on an input image, and carrying out mean value removal on the image;
for each deep convolutional neural network model, calculating a quality evaluation score of the input image through a deep convolutional neural network forward reasoning calculation process; outputting the score probability of the image data belonging to different grades at the last soft-max; calculate mean and standard deviation for score probability:
and respectively calculating the average value and the average value of the standard deviation calculated by each depth convolution neural network model, using the average values and the average values as image quality evaluation indexes, and evaluating the image quality according to the numerical values of the image quality evaluation indexes.
5. An electric transmission and transformation inspection image quality evaluation system, which is characterized by comprising a server, wherein the server comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, and the processor executes the program to realize the electric transmission and transformation inspection image quality evaluation method based on the deep convolutional neural network according to any one of claims 1 to 4.
6. A computer-readable storage medium having stored thereon a computer program, characterized in that the program, when executed by a processor, performs the power transmission and transformation inspection image quality evaluation method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811532907.7A CN109615627B (en) | 2018-12-14 | 2018-12-14 | Power transmission and transformation inspection image quality evaluation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811532907.7A CN109615627B (en) | 2018-12-14 | 2018-12-14 | Power transmission and transformation inspection image quality evaluation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109615627A CN109615627A (en) | 2019-04-12 |
| CN109615627B true CN109615627B (en) | 2021-07-27 |
Family
ID=66009423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811532907.7A Active CN109615627B (en) | 2018-12-14 | 2018-12-14 | Power transmission and transformation inspection image quality evaluation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109615627B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210558B (en) * | 2019-05-31 | 2021-10-26 | 北京市商汤科技开发有限公司 | Method and device for evaluating performance of neural network |
| CN111325711A (en) * | 2020-01-16 | 2020-06-23 | 杭州德适生物科技有限公司 | Chromosome split-phase image quality evaluation method based on deep learning |
| CN111818363A (en) * | 2020-07-10 | 2020-10-23 | 携程计算机技术（上海）有限公司 | Short video extraction method, system, device and storage medium |
| CN113158777A (en) * | 2021-03-08 | 2021-07-23 | 佳都新太科技股份有限公司 | Quality scoring method, quality scoring model training method and related device |
| CN113496485B (en) * | 2021-06-24 | 2022-12-02 | 北京市遥感信息研究所 | Satellite remote sensing image quality evaluation method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503366A (en) * | 2016-10-27 | 2017-03-15 | 石家庄铁道大学 | The method for suppressing EMD end effects |
| CN107743225A (en) * | 2017-10-16 | 2018-02-27 | 杭州电子科技大学 | It is a kind of that the method for carrying out non-reference picture prediction of quality is characterized using multilayer depth |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544705B (en) * | 2013-10-25 | 2016-03-02 | 华南理工大学 | A kind of image quality test method based on degree of depth convolutional neural networks |
| US9779492B1 (en) * | 2016-03-15 | 2017-10-03 | International Business Machines Corporation | Retinal image quality assessment, error identification and automatic quality correction |
| US10002415B2 (en) * | 2016-04-12 | 2018-06-19 | Adobe Systems Incorporated | Utilizing deep learning for rating aesthetics of digital images |
| CN107633513B (en) * | 2017-09-18 | 2021-08-17 | 天津大学 | 3D image quality measuring method based on deep learning |
| CN107610123A (en) * | 2017-10-11 | 2018-01-19 | 中共中央办公厅电子科技学院 | A kind of image aesthetic quality evaluation method based on depth convolutional neural networks |
| CN108377387A (en) * | 2018-03-22 | 2018-08-07 | 天津大学 | Virtual reality method for evaluating video quality based on 3D convolutional neural networks |
| CN108596902B (en) * | 2018-05-04 | 2020-09-08 | 北京大学 | Multi-task full-reference image quality evaluation method based on gating convolutional neural network |
| CN108897797A (en) * | 2018-06-12 | 2018-11-27 | 腾讯科技（深圳）有限公司 | Update training method, device, storage medium and the electronic equipment of dialog model |
| CN108960087A (en) * | 2018-06-20 | 2018-12-07 | 中国科学院重庆绿色智能技术研究院 | A kind of quality of human face image appraisal procedure and system based on various dimensions evaluation criteria |
-
2018
- 2018-12-14 CN CN201811532907.7A patent/CN109615627B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503366A (en) * | 2016-10-27 | 2017-03-15 | 石家庄铁道大学 | The method for suppressing EMD end effects |
| CN107743225A (en) * | 2017-10-16 | 2018-02-27 | 杭州电子科技大学 | It is a kind of that the method for carrying out non-reference picture prediction of quality is characterized using multilayer depth |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109615627A (en) | 2019-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109615627B (en) | Power transmission and transformation inspection image quality evaluation method and system | |
| CN108615071B (en) | Model testing method and device | |
| CN106971152B (en) | Method for detecting bird nest in power transmission line based on aerial images | |
| CN109559310B (en) | Power transmission and transformation inspection image quality evaluation method and system based on significance detection | |
| CN111739076B (en) | Unsupervised content protection domain adaptation method for multiple CT lung texture recognition | |
| CN111444821A (en) | Automatic identification method for urban road signs | |
| CN109858569A (en) | Multi-tag object detecting method, system, device based on target detection network | |
| CN111650453B (en) | Power equipment diagnosis method and system based on windowing characteristic Hilbert imaging | |
| CN106447646A (en) | Quality blind evaluation method for unmanned aerial vehicle image | |
| CN110135282B (en) | Examinee return plagiarism cheating detection method based on deep convolutional neural network model | |
| CN109214298B (en) | Asian female color value scoring model method based on deep convolutional network | |
| CN106897998B (en) | Method and system for predicting information of direct solar radiation intensity | |
| CN113313107A (en) | Intelligent detection and identification method for multiple types of diseases on cable surface of cable-stayed bridge | |
| CN110782448A (en) | Rendered image evaluation method and device | |
| CN114881997A (en) | Wind turbine generator defect assessment method and related equipment | |
| CN115620178A (en) | Real-time detection method for abnormal and dangerous behaviors of power grid of unmanned aerial vehicle | |
| CN114998251A (en) | Air multi-vision platform ground anomaly detection method based on federal learning | |
| CN111539250B (en) | Image fog concentration estimation method, system and terminal based on neural network | |
| Su | Data research on tobacco leaf image collection based on computer vision sensor | |
| CN117173595A (en) | Unmanned aerial vehicle aerial image target detection method based on improved YOLOv7 | |
| CN116452904A (en) | Image aesthetic quality determination method | |
| CN113627302B (en) | Ascending construction compliance detection method and system | |
| Liu et al. | A novel image segmentation algorithm based on visual saliency detection and integrated feature extraction | |
| CN111402397B (en) | TOF depth data optimization method and device based on unsupervised data | |
| CN114359727B (en) | Tea disease identification method and system based on lightweight optimization Yolo v4 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 250001, No. two, No. 150, Ji'nan, Shandong Applicant after: State Grid Shandong Electric Power Company Information Communication Company Applicant after: National Network Intelligent Technology Co., Ltd. Applicant after: State Grid Co., Ltd. Address before: 250001, No. two, No. 150, Ji'nan, Shandong Applicant before: State Grid Shandong Electric Power Company Information Communication Company Applicant before: Shandong Luneng Intelligent Technology Co., Ltd. Applicant before: State Grid Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201026 Address after: 250101 Electric Power Intelligent Robot Production Project 101 in Jinan City, Shandong Province, South of Feiyue Avenue and East of No. 26 Road (ICT Industrial Park) Applicant after: National Network Intelligent Technology Co.,Ltd. Address before: 250001, No. two, No. 150, Ji'nan, Shandong Applicant before: INFORMATION COMMUNICATION COMPANY OF STATE GRID SHANDONG ELECTRIC POWER Co. Applicant before: National Network Intelligent Technology Co.,Ltd. Applicant before: STATE GRID CORPORATION OF CHINA |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |